Systems and methods for generating and updating a value of personal possessions of a user for insurance purposes

Abstract

A computing system including a processor in communication with a memory device for generating a predicted one or more values of personal property items associated with a candidate user enrolling in an insurance policy may be provided. The processor may be configured to: (i) generate a predictive possession value model based at least in part upon a plurality of historical policyholder records, (ii) receive personal and property data associated with the candidate user, (iii) predict a one or more values associated with one or more items owned by the candidate user, (iv) determine a maximum reimbursement amount for the candidate user, (v) receive a claim associated with the candidate user in response to a claim event, wherein the claim includes a list of lost items and/or a list of spared items, (vi) estimate a value associated with the lists of lost items and/or spared items, (vii) adjust the maximum reimbursement amount based at least in part upon the estimated value, and (viii) determine an actual reimbursement amount for the candidate user.

What is claimed: 
     
       1. A computing system for generating one or more predicted values of one or more personal property items owned by a candidate user, the computing system including at least one processor in communication with at least one memory device, the at least one processor configured to:
 generate a predictive possession value model based at least in part upon a plurality of historical policyholder records associated with a plurality of policyholders, by
 utilizing a machine learning model to predict one or more item values of one or more items owned by each policyholder of the plurality of policyholders based at least in part upon personal data and property data associated with each policyholder of the plurality of policyholders, 
 wherein the plurality of historical policyholder records include (i) historical policy data including the one or more item values associated with the one or more items owned by each policyholder of the plurality of policyholders and historical insurance claim data associated with the plurality of policyholders, (ii) the personal data associated with each policyholder of the plurality of policyholders, and (iii) the property data associated with each policyholder of the plurality of policyholders; 
 
 receive personal data and property data associated with the candidate user; 
 determine, based at least in part upon the generated predictive possession model, the one or more predicted values of the one or more personal property items owned by the candidate user based at least in part upon the received personal data and the received property data; 
 determine a maximum reimbursement amount for the candidate user based at least in part upon the one or more predicted values; 
 receive a claim associated with the candidate user in response to a claim event, wherein the claim includes one of a list of lost items and a list of spared items; 
 estimate a claim value associated with the claim based at least in part on the list of lost items and the list of spared items; 
 adjust the maximum reimbursement amount based at least in part upon the estimated claim value associated with the claim; 
 determine an actual reimbursement amount for the candidate user based at least in part upon the adjusted maximum reimbursement; and 
 provide the actual reimbursement amount to the candidate user, wherein the actual reimbursement amount is provided in a form of at least one selected from a group consisting of a check, a direct deposit, cash, a digital wallet credit, and a prepaid card. 
 
     
     
       2. The computing system of  claim 1 , wherein the at least one processor is further configured to:
 prompt the candidate user to at least one of adjust the one or more predicted values and accept the one or more predicted values; and 
 store, in the at least one memory device, at least one of the one or more adjusted predicted values and the one or more accepted predicted values. 
 
     
     
       3. The computing system of  claim 1 , wherein the at least one processor is further configured to:
 continually retrieve one or more additional historical policyholder records; 
 update the predictive possession value model based at least in part upon the one or more additional historical policyholder records; and 
 store, in the at least one memory device, the updated predictive possession value model. 
 
     
     
       4. The computing system of  claim 1 , wherein the at least one processor is configured to adjust the maximum reimbursement amount by:
 reducing the determined maximum reimbursement amount by one or more values associated with the list of spared items. 
 
     
     
       5. The computing system of  claim 4 , wherein the at least one processor is configured to adjust the maximum reimbursement amount by:
 estimating the one or more values associated with the list of spared items at least by comparing one or more values associated with the list of lost items to the one or more predicted values; and 
 reducing the determined maximum reimbursement amount by the one or more estimated values associated with the list of spared items. 
 
     
     
       6. The computing system of  claim 1 , wherein the personal data of the candidate user includes at least one selected from a group consisting of demographic data, age data, marital status, education, and employment data associated with the candidate user, and wherein the property data of the candidate user includes one of residency data, location data, and square footage data associated with a residence of the candidate user. 
     
     
       7. A computer-implemented method for generating one or more predicted values of one or more personal property items owned by a candidate user, the method implemented on a computer device including at least one processor in communication with at least one memory device, said method comprising:
 generating a predictive possession value model based at least in part upon a plurality of historical policyholder records associated with a plurality of policyholders, by
 utilizing a machine learning model to predict one or more item values of one or more items owned by each policyholder of the plurality of policyholders based at least in part upon personal data and property data associated with each policyholder of the plurality of policyholders, 
 wherein the plurality of historical policyholder records includes (i) historical policy data including the one or more item values associated with the one or more items owned by each policyholder of the plurality of policyholders, (ii) the personal data associated with each policyholder of the plurality of policyholders, and (iii) the property data associated with each policyholder of the plurality of policyholders; 
 
 receiving personal data and property data associated with the candidate user; 
 determining, based at least in part upon the generated predictive possession model, the one or more predicted values of the one or more personal property items owned by the candidate user based at least in part upon the received personal data and the received property data; 
 determining a maximum reimbursement amount for the candidate user based at least in part upon the one or more predicted values; 
 receiving a claim associated with the candidate user in response to a claim event, wherein the claim includes one of a list of lost items and a list of spared items; 
 estimating a claim value associated with the claim based at least in part on the list of lost items and the list of spared items; 
 adjusting the maximum reimbursement amount based at least in part upon the estimated claim value associated with the claim; 
 determining an actual reimbursement amount for the candidate user based at least in part upon the adjusted maximum reimbursement; and 
 providing the actual reimbursement amount to the candidate user, wherein the actual reimbursement amount is provided in a form of at least one selected from a group consisting of a check, a direct deposit, cash, a digital wallet credit, and a prepaid card. 
 
     
     
       8. The method of  claim 7  further comprising:
 prompting the candidate user to at least one of adjust the predicted one or more values and accept the one or more predicted values; and 
 storing, in the at least one memory device, at least one selected from a group consisting of the one or more adjusted predicted values and the one or more accepted predicted values. 
 
     
     
       9. The method of  claim 7  further comprising:
 continually retrieving one or more additional historical policyholder records; 
 updating the predictive possession value model based at least in part upon the one or more additional historical policyholder records; and 
 storing, in the at least one memory device, the updated predictive possession value model. 
 
     
     
       10. The method of  claim 7 , wherein the adjusting the maximum reimbursement amount includes:
 reducing the determined maximum reimbursement by one or more values associated with the list of spared items. 
 
     
     
       11. The method of  claim 10 , wherein the adjusting the maximum reimbursement amount includes:
 estimating the one or more values associated with the list of spared items at least by comparing one or more values associated with the list of lost items to the one or more predicted values; and 
 reducing the determined maximum reimbursement by the one or more estimated values of the list of spared items. 
 
     
     
       12. At least one non-transitory computer-readable media having computer-executable instructions thereon, wherein when executed by at least one processor of a computing device in communication with at least one memory device, cause the at least one processor to:
 generate a predictive possession value model based at least in part upon a plurality of historical policyholder records associated with a plurality of policyholders, by
 utilizing a machine learning model to predict one or more item values of one or more items owned by each policyholder of the plurality of policyholders based at least in part upon personal data and property data associated with each policyholder of the plurality of policyholders, 
 wherein the plurality of historical policyholder records include (i) historical policy data including the one or more item values associated with the one or more items owned by each policyholder of the plurality of policyholders, (ii) the personal data associated with each policyholder of the plurality of policyholders, and (iii) the property data associated with each policyholder of the plurality of policyholders; 
 
 receive personal data and property data associated with the candidate user; 
 determine, based at least in part upon the generated predictive possession model, the one or more predicted values of the one or more personal property items owned by the candidate user based at least in part upon the received personal data and the received property data; 
 determine a maximum reimbursement amount for the candidate user based at least in part upon the one or more predicted values; 
 receive a claim associated with the candidate user in response to a claim event, wherein the claim includes one of a list of lost items and a list of spared items; 
 estimate a value associated with the claim based at least in part on the list of lost items and the list of spared items; 
 adjust the maximum reimbursement amount based at least in part upon the estimated claim value associated with the claim; 
 determine an actual reimbursement amount for the candidate user based at least in part upon the adjusted maximum reimbursement; and 
 provide the actual reimbursement amount to the candidate user, wherein the actual reimbursement amount is provided in a form of at least one selected from a group consisting of a check, a direct deposit, cash, a digital wallet credit, and a prepaid card. 
 
     
     
       13. The computer-readable media of  claim 12 , wherein the computer-executable instructions further cause the at least one processor to:
 prompt the candidate user to at least one of adjust the one or more predicted values and accept the one or more predicted values; and 
 store, in the at least one memory device, at least one selected from a group consisting of the one or more adjusted predicted values and the one or more accepted predicted values. 
 
     
     
       14. The computer-readable media of  claim 12 , wherein the computer-executable instructions further cause the at least one processor to:
 continually retrieve one or more additional historical policyholder records; 
 update the predictive possession value model based at least in part upon the one or more additional historical policyholder records; and 
 store, in the at least one memory device, the updated predictive possession value model.